From 2eca16c61d6965ba13b028305192afb2e493d126 Mon Sep 17 00:00:00 2001 From: xizhuomengcontin Date: Sat, 10 Oct 2026 17:46:01 +0800 Subject: [PATCH 1/2] Qualify the fork claim: available checkpoints, not any step Review was right. deriveCheckpoints requires both a complete conversation prefix and a filesystem snapshot, and `replay --fork` rejects a run with no checkpoints and snaps a non-checkpoint --from back to the nearest prior one (fork.snapped). The entry now says it forks from available checkpoints. Also dropped "offline" from the same sentence -- replay withholds the model provider, it does not take the run off the network -- and said so explicitly. Regenerated README; validate, diff --check and check-links all clean. Co-Authored-By: Claude Opus 5 (1M context) --- README.md | 1 + data/projects.json | 13 +++++++++++++ 2 files changed, 14 insertions(+) diff --git a/README.md b/README.md index 275f4e2..5bbf43a 100644 --- a/README.md +++ b/README.md @@ -154,6 +154,7 @@ AI agents that write, debug, and maintain code autonomously. - [**Open SWE**](https://github.com/langchain-ai/open-swe#readme) - Open-source asynchronous coding agent by LangChain for software engineering tasks. by [@langchain-ai](https://github.com/langchain-ai) (10,814 stars) - [**Mini-SWE-Agent**](https://github.com/SWE-agent/mini-swe-agent#readme) - The 100-line AI agent that solves GitHub issues. Radically simple but scores >74% on SWE-bench verified. by [@SWE-agent](https://github.com/SWE-agent) (8,255 stars) - [**Reflexion**](https://github.com/noahshinn/reflexion#readme) - Language agents with verbal reinforcement learning. Agents that learn from mistakes through self-reflection. by [@noahshinn](https://github.com/noahshinn) (3,295 stars) +- [**OrcaReplay**](https://github.com/Continuum-AI-Corp/OrcaReplay#readme) - Records a coding agent's exchange with its model provider and replays the run without calling the provider; replay can fork from available checkpoints onto a different model. Recorded tool calls still execute on replay. by [@Continuum-AI-Corp](https://github.com/Continuum-AI-Corp) (268 stars) - [**Autohand Code**](https://github.com/autohandai/code-cli#readme) - Self-evolving coding agent that runs in your terminal. by [@autohandai](https://github.com/autohandai) (202 stars) diff --git a/data/projects.json b/data/projects.json index 1c8b154..6cf92c9 100644 --- a/data/projects.json +++ b/data/projects.json @@ -1562,5 +1562,18 @@ "research" ], "stars": 252 + }, + { + "name": "OrcaReplay", + "repo": "Continuum-AI-Corp/OrcaReplay", + "description": "Records a coding agent's exchange with its model provider and replays the run without calling the provider; replay can fork from available checkpoints onto a different model. Recorded tool calls still execute on replay.", + "category": "coding", + "maintainer": "Continuum-AI-Corp", + "tags": [ + "record-replay", + "observability", + "cli" + ], + "stars": 268 } ] From a4918c1cf8e8d229d7ab4df6d2ea2c6913fe6c1e Mon Sep 17 00:00:00 2001 From: autogame-17 <17@evomap.ai> Date: Tue, 20 Oct 2026 22:14:59 +0800 Subject: [PATCH 2/2] fix: refresh OrcaReplay catalog metadata Refresh the canonical star snapshot while preserving the reviewed replay description. Co-Authored-By: Claude Sonnet 5.5 --- data/projects.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/data/projects.json b/data/projects.json index 6cf92c9..b2372bc 100644 --- a/data/projects.json +++ b/data/projects.json @@ -1574,6 +1574,6 @@ "observability", "cli" ], - "stars": 268 + "stars": 286 } ]